one hot for new data : what to do if new unseen in training data set categories are located in test data

[Sandy4321]

great code thanks
Practical-Deep-Learning-for-Coders-2.0/Tabular Notebooks/02_Bayesian_Optimization.ipynb

only can you clarify what to do with tabular data embedding's if new unseen in training data set categories are located in test data

it is very practicable case when new observation are located in data for prediction

for example feature month has only January and February on train data
but there are march and June in test data?

there is not one hot representation for new data
does it mean new values will be converted to all 0s or code just will crush ?

[Sandy4321]

may be it is treated atomically as written here

the extra dimension is used when encountering a previously unseen value

https://medium.com/codon-consulting/using-entity-embeddings-with-fastai-v1-and-v2-fa4ba0d80105